Geekbench ML Score

688
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 04:10 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 7
Model IDiPhone9,3
Motherboard D101AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 569
61.0 IPS
 
Image Classification (F16)
100% 582
62.4 IPS
 
Image Classification (I8)
81% 292
31.3 IPS
 
Image Segmentation (F32)
100% 1544
9.54 IPS
 
Image Segmentation (F16)
100% 2575
15.9 IPS
 
Image Segmentation (I8)
89% 530
3.27 IPS
 
Pose Estimation (F32)
100% 644
2.60 IPS
 
Pose Estimation (F16)
100% 1213
4.91 IPS
 
Pose Estimation (I8)
80% 101
0.41 IPS
 
Object Detection (F32)
100% 945
33.2 IPS
 
Object Detection (F16)
100% 1179
41.4 IPS
 
Object Detection (I8)
52% 382
13.4 IPS
 
Face Detection (F32)
100% 1493
17.2 IPS
 
Face Detection (F16)
97% 2715
31.2 IPS
 
Face Detection (I8)
75% 350
4.02 IPS
 
Text Classification (F32)
100% 430
169.9 IPS
 
Text Classification (F16)
98% 580
229.6 IPS
 
Machine Translation (F32)
100% 584
90.0 IPS
 
Machine Translation (F16)
100% 587
90.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download